diff --git a/assets/logos/uomirouter-dark.png b/assets/logos/uomirouter-dark.png
new file mode 100644
index 0000000000..d7abfc8b0e
Binary files /dev/null and b/assets/logos/uomirouter-dark.png differ
diff --git a/assets/logos/uomirouter-light.png b/assets/logos/uomirouter-light.png
new file mode 100644
index 0000000000..2bbf3133c1
Binary files /dev/null and b/assets/logos/uomirouter-light.png differ
diff --git a/docs/inference-providers/_toctree.yml b/docs/inference-providers/_toctree.yml
index 4623dd474f..f887935030 100644
--- a/docs/inference-providers/_toctree.yml
+++ b/docs/inference-providers/_toctree.yml
@@ -138,6 +138,8 @@
     title: Scaleway
   - local: providers/together
     title: Together
+  - local: providers/uomirouter
+    title: UomiRouter
   - local: providers/wavespeed
     title: WaveSpeedAI
   - local: providers/zai-org
diff --git a/docs/inference-providers/index.md b/docs/inference-providers/index.md
index 4572e7c280..5b7df276b7 100644
--- a/docs/inference-providers/index.md
+++ b/docs/inference-providers/index.md
@@ -30,6 +30,7 @@ Our platform integrates with leading AI infrastructure providers, giving you acc
 | [SambaNova](./providers/sambanova)           |          ✅           |                       |         ✅         |               |               |                |
 | [Scaleway](./providers/scaleway)             |          ✅           |                       |         ✅         |               |               |                |
 | [Together](./providers/together)             |          ✅           |          ✅           |                    |      ✅       |               |                |
+| [UomiRouter](./providers/uomirouter)         |          ✅           |          ✅           |                    |               |               |                |
 | [WaveSpeedAI](./providers/wavespeed)         |                       |                       |                    |      ✅       |      ✅       |                |
 | [Z.ai](./providers/zai-org)                  |          ✅           |          ✅           |                    |               |               |                |
 
diff --git a/docs/inference-providers/providers/uomirouter.md b/docs/inference-providers/providers/uomirouter.md
new file mode 100644
index 0000000000..62dab602da
--- /dev/null
+++ b/docs/inference-providers/providers/uomirouter.md
@@ -0,0 +1,66 @@
+<!---
+WARNING
+
+This markdown file has been generated from a script. Please do not edit it directly.
+
+### Template
+
+If you want to update the content related to uomirouter's description, please edit the template file under `https://github.com/huggingface/hub-docs/tree/main/scripts/inference-providers/templates/providers/uomirouter.handlebars`.
+
+### Logos
+
+If you want to update uomirouter's logo, upload a file by opening a PR on https://huggingface.co/datasets/huggingface/documentation-images/tree/main/inference-providers/logos. Ping @wauplin and @celinah on the PR to let them know you uploaded a new logo.
+Logos must be in .png format and be named `uomirouter-light.png` and `uomirouter-dark.png`. Visit https://huggingface.co/settings/theme to switch between light and dark mode and check that the logos are displayed correctly.
+
+### Generation script
+
+For more details, check out the `generate.ts` script: https://github.com/huggingface/hub-docs/blob/main/scripts/inference-providers/scripts/generate.ts.
+--->
+
+# UomiRouter
+
+> [!TIP]
+> All supported UomiRouter models can be found [here](https://huggingface.co/models?inference_provider=uomirouter&sort=trending)
+
+<div class="flex justify-center">
+    <a href="https://uomirouter.uomi.ai/" target="_blank">
+        <img class="block dark:hidden" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/inference-providers/logos/uomirouter-light.png"/>
+        <img class="hidden dark:block" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/inference-providers/logos/uomirouter-dark.png"/>
+    </a>
+</div>
+
+<div class="flex">
+    <a href="https://huggingface.co/uomi-network" target="_blank">
+        <img class="block dark:hidden" src="https://huggingface.co/datasets/huggingface/badges/resolve/main/follow-us-on-hf-lg.svg"/>
+        <img class="hidden dark:block" src="https://huggingface.co/datasets/huggingface/badges/resolve/main/follow-us-on-hf-lg-dark.svg"/>
+    </a>
+</div>
+
+UomiRouter is an OpenAI-compatible inference network. Inference traffic is served by **accredited operator nodes that are part of the UOMI network** — each operator runs the engine container on their own GPU hardware (datacenter or homelab) and is admitted after a hardware + reliability vetting. Operators commit to a strict privacy policy (no prompt logging, no training-data collection), payload obfuscation in transit and at rest, and **OPoC (Off-chain Proof of Computation)**: every response is signed by the operator's wallet key and carries a SHA256 of the output (returned as `x-wallet-signature` / `x-wallet-pubkey` headers), and a sampled fraction is cross-dispatched to an independent operator for re-verification. The on-chain anchoring layer on UOMI L1 is the next milestone and is not live yet.
+
+Endpoints are served from EU, US and APAC regions through a single public gateway at `https://gateway.uomi.ai`. Per-model pricing is exposed via `/v1/models` (`pricing.input` / `pricing.output`, USD per million tokens). Inference payloads are retained for 7 days for billing reconciliation only — never used for training. Full provider documentation lives at [https://uomirouter.uomi.ai/docs](https://uomirouter.uomi.ai/docs).
+
+## Supported tasks
+
+
+### Chat Completion (LLM)
+
+Find out more about Chat Completion (LLM) [here](../tasks/chat-completion).
+
+<InferenceSnippet
+    pipeline=text-generation
+    providersMapping={ {"uomirouter":{"modelId":"Qwen/Qwen3.6-27B","providerModelId":"qwen/qwen3.6-27b"} } }
+conversational />
+
+
+### Chat Completion (VLM)
+
+Find out more about Chat Completion (VLM) [here](../tasks/chat-completion).
+
+<InferenceSnippet
+    pipeline=image-text-to-text
+    providersMapping={ {"uomirouter":{"modelId":"google/gemma-4-31B-it","providerModelId":"google/gemma-4-31B-it"} } }
+conversational />
+
+
+---
diff --git a/scripts/inference-providers/scripts/generate.ts b/scripts/inference-providers/scripts/generate.ts
index 9078a6f4ae..049b12ea59 100644
--- a/scripts/inference-providers/scripts/generate.ts
+++ b/scripts/inference-providers/scripts/generate.ts
@@ -53,6 +53,7 @@ const PROVIDERS_URLS: Record<string, string> = {
   sambanova: "https://sambanova.ai/",
   scaleway: "https://www.scaleway.com",
   together: "https://together.xyz/",
+  uomirouter: "https://uomirouter.uomi.ai/",
   wavespeed: "https://wavespeed.ai/",
   "zai-org": "https://z.ai/"
 };
diff --git a/scripts/inference-providers/templates/providers/uomirouter.handlebars b/scripts/inference-providers/templates/providers/uomirouter.handlebars
new file mode 100644
index 0000000000..ea59d35eb6
--- /dev/null
+++ b/scripts/inference-providers/templates/providers/uomirouter.handlebars
@@ -0,0 +1,14 @@
+# UomiRouter
+
+> [!TIP]
+> All supported UomiRouter models can be found [here](https://huggingface.co/models?inference_provider=uomirouter&sort=trending)
+
+{{{logoSection}}}
+
+{{{followUsSection}}}
+
+UomiRouter is an OpenAI-compatible inference network. Inference traffic is served by **accredited operator nodes that are part of the UOMI network** — each operator runs the engine container on their own GPU hardware (datacenter or homelab) and is admitted after a hardware + reliability vetting. Operators commit to a strict privacy policy (no prompt logging, no training-data collection), payload obfuscation in transit and at rest, and **OPoC (Off-chain Proof of Computation)**: every response is signed by the operator's wallet key and carries a SHA256 of the output (returned as `x-wallet-signature` / `x-wallet-pubkey` headers), and a sampled fraction is cross-dispatched to an independent operator for re-verification. The on-chain anchoring layer on UOMI L1 is the next milestone and is not live yet.
+
+Endpoints are served from EU, US and APAC regions through a single public gateway at `https://gateway.uomi.ai`. Per-model pricing is exposed via `/v1/models` (`pricing.input` / `pricing.output`, USD per million tokens). Inference payloads are retained for 7 days for billing reconciliation only — never used for training. Full provider documentation lives at [https://uomirouter.uomi.ai/docs](https://uomirouter.uomi.ai/docs).
+
+{{{tasksSection}}}